commit 2b37b2cac5dbf53196c81771d2377892659f29b9 Author: ModelHub XC Date: Mon Aug 3 14:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-lust-8b-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75a2b7e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-lust-8b-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7608b9c --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Fizzarolli/llama-3-lust-8b-v0.2 +language: +- en +library_name: transformers +license: other +license_name: llama3 +quantized_by: mradermacher +tags: +- axolotl +--- +## About + + + + + + +static quants of https://huggingface.co/Fizzarolli/llama-3-lust-8b-v0.2 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-lust-8b-v0.2-GGUF/resolve/main/llama-3-lust-8b-v0.2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/llama-3-lust-8b-v0.2.IQ4_XS.gguf b/llama-3-lust-8b-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..3a5a255 --- /dev/null +++ b/llama-3-lust-8b-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ef320dbf4b156f1e23477fa74a42d56457fbc114977b41bc459f1a4a97adbf +size 4484362912 diff --git a/llama-3-lust-8b-v0.2.Q2_K.gguf b/llama-3-lust-8b-v0.2.Q2_K.gguf new file mode 100644 index 0000000..0eed04c --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97710153a81bf4b363badb383df983a7ecf4d0167f29e1360eb4276d374df287 +size 3179131552 diff --git a/llama-3-lust-8b-v0.2.Q3_K_L.gguf b/llama-3-lust-8b-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..e1f13e6 --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb1e958b76ef1ae4ebd8567e94c7ce72092544eff9ff278128300023a4227c9 +size 4321956512 diff --git a/llama-3-lust-8b-v0.2.Q3_K_M.gguf b/llama-3-lust-8b-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..cc73010 --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24bf8c70aa6b5077c2f7657033e59fc5500206ad83b04a7d6a9eac3a1d763b57 +size 4018918048 diff --git a/llama-3-lust-8b-v0.2.Q3_K_S.gguf b/llama-3-lust-8b-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..926d246 --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fbc18d59e0da237969b7c12ddd2b91b5d4a15391ba75e669fa5b4dbf5bd9661 +size 3664499360 diff --git a/llama-3-lust-8b-v0.2.Q4_K_M.gguf b/llama-3-lust-8b-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..711833a --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9175df7c32c4bf3fcd1c18dd81c5757545968ef0587d10114c4a544cdaac8d +size 4920734368 diff --git a/llama-3-lust-8b-v0.2.Q4_K_S.gguf b/llama-3-lust-8b-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..bd7226d --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1315f2609865d698a3f1a397462764a00c3a4b32591e388752a134aba3878cd8 +size 4692669088 diff --git a/llama-3-lust-8b-v0.2.Q5_K_M.gguf b/llama-3-lust-8b-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..fcde82f --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a517109e7f8c6e3bfc7823d8e8ffbb7b55b4574e8e3030f9862dd650a178d75 +size 5732987552 diff --git a/llama-3-lust-8b-v0.2.Q5_K_S.gguf b/llama-3-lust-8b-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..1147b8e --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4bb7aa5e8e17d62688d17398f71e022c567425eed9c71c6b743b38f53f7b86 +size 5599294112 diff --git a/llama-3-lust-8b-v0.2.Q6_K.gguf b/llama-3-lust-8b-v0.2.Q6_K.gguf new file mode 100644 index 0000000..84a0c2c --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6640c6fa346a5152b54baacd7dfc1be76e7e8c471c654e31e4cf00ce73e1a8 +size 6596006560 diff --git a/llama-3-lust-8b-v0.2.Q8_0.gguf b/llama-3-lust-8b-v0.2.Q8_0.gguf new file mode 100644 index 0000000..56ed534 --- /dev/null +++ b/llama-3-lust-8b-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e05d9f045bef0dac8daa3ed82456f1c6f8558bce635c25283738cb90a3e1ebe +size 8540770976 diff --git a/llama-3-lust-8b-v0.2.f16.gguf b/llama-3-lust-8b-v0.2.f16.gguf new file mode 100644 index 0000000..403db07 --- /dev/null +++ b/llama-3-lust-8b-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6d6b9bd118ee86825ab7775882c3ea829d358ee896ab95d868e720f15255a0 +size 16068891296